Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3936 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.5349. Min Act: -0.0000

Data Index: 1243851 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.3411. Min Act: -0.0000

Data Index: 603036 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.6304. Min Act: -0.0000

Data Index: 478597 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.3131. Min Act: -0.0000

Data Index: 1231467 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.2703. Min Act: -0.0000

Data Index: 1344179 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.1323. Min Act: -0.0000

Data Index: 1252148 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.3324. Min Act: -0.0000

Data Index: 1345117 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.1088. Min Act: -0.0000

Data Index: 127920 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.1006. Min Act: -0.0000

Data Index: 570958 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 2.6304. Min Range: -2.6304

Max Act: 1.9866. Min Act: -0.0001

Data Index: 1234647 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.2839. Min Act: -0.0001

Data Index: 15491 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.1495. Min Act: -0.0000

Data Index: 10326 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.0210. Min Act: -0.0000

Data Index: 1181279 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.1293. Min Act: -0.0000

Data Index: 158214 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.0122. Min Act: -0.0000

Data Index: 116427 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.2390. Min Act: -0.0000

Data Index: 742816 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.0311. Min Act: -0.0000

Data Index: 10721 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 2.6304. Min Range: -2.6304

Max Act: 1.9358. Min Act: -0.0000

Data Index: 936885 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 2.6304. Min Range: -2.6304

Max Act: 2.0155. Min Act: -0.0000

Data Index: 1243990 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 2.6304. Min Range: -2.6304

Max Act: 1.9026. Min Act: -0.0000

Data Index: 553862 (C4 (Web Text))

Max Activating Token Index: 540